Skip to main content
All CollectionsAnalysing results
AI summaries for qualitative data
AI summaries for qualitative data

Discover more about our latest feature that helps to summarize open text & video responses

Updated over a month ago

We have introduced a beta feature that leverages AI to generate summaries for your qualitative question types, such as open text and video responses. With this new tool, you can quickly review key themes and insights directly within your results dashboard, making it easier to analyse and understand your data.

How Does It Work?

  • For open text and video responses, you'll now see a "Summarise" button

  • When you click this button, an AI model will generate a concise summary of the responses for that question in just a few seconds.

  • The summary will present 3–5 key bullet points, highlighting the most important themes and insights—saving you time and allowing you to focus on what matters most.

  • The quality of the summary generated depends on the quality and quantity of the input, so the more responses you provide, the more accurate the summary will be.

  • This feature is powered by an external generative AI model, overseen by our expert Data Team. You’ll see more detail on this below.

  • The summary will always be in English but will incorporate answers entered in other languages.

Which AI model is used?

This feature uses a carefully selected AWS AI model to complete tasks such as summarising open-text responses, or transcripts from our video response feature.

How is my data used?

In short - it’s not. To produce summaries, the AI model only utilises respondents’ survey text, and not customer data.

Survey responses do not contain any personally identifiable information, and only the anonymous response text data is utilised to ensure that individuals cannot be identified.

We have broad opt-outs in place to ensure that any data provided by Attest is not used to train AWS’ models. For more information see our FAQ.

What does ‘Beta’ mean?

At Attest, we use betas to share features we are actively working on with our customers to get early insight into how well they work and collect feedback on how to improve them.

Beta features may be made available for a limited time while we assess the value and figure out how it fits into our product offering on a long term basis. Learn more about betas here.

Did this answer your question?